Re: [R] Pruning trees in a Random Forest

From: Liaw, Andy <andy_liaw_at_merck.com>
Date: Sun, 22 Mar 2009 14:25:42 -0400

Jerry Friedman advocated a few mods to RF in his "ISLE" algorithm:  

Andy


From: Wensui Liu [mailto:liuwensui_at_gmail.com] Sent: Fri 3/20/2009 4:46 PM
To: Liaw, Andy
Cc: Anirudh Kondaveeti; r-help_at_r-project.org Subject: Re: [R] Pruning trees in a Random Forest

I don't think it necessary to prune trees in RF, per brieman's paper.

On 3/20/09, Liaw, Andy <andy_liaw_at_merck.com> wrote:
> The way the trees are structured in randomForest, there's no way to stop
> tree growth by depth (what you called level).
>
> (If anyone has ideas, I'm all ears.)
>
> Andy
>
> From: Anirudh Kondaveeti
>>
>> Hi all!
>>
>> The randomForest in R enables us to prune the trees using the nodesize
>> feature where we can stop splitting a node if it contains
>> less than the
>> specified no.of of records/entities at that node.
>>
>> However is there a way to stop the tree growing after a
>> specified number of
>> levels. To be more clear on what I mean by a level. Level 0
>> is the parent
>> node, Level 1 has 2 daughter nodes, Level 2 has 4 daughter
>> nodes, Level 3
>> has 8 daughter nodes etc.
>>
>> Thanks in advance!
>>
>> Anirudh Kondaveeti
>> ----------------------------
>>
>> [[alternative HTML version deleted]]
>>
>> ______________________________________________
>> R-help_at_r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>>
> Notice: This e-mail message, together with any attachme...{{dropped:12}}
>
> ______________________________________________
> R-help_at_r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

--
==============================
WenSui Liu
Acquisition Risk, Chase
Blog   : statcompute.spaces.live.com

Tough Times Never Last. But Tough People Do.  - Robert Schuller
==============================


Notice:  This e-mail message, together with any attachme...{{dropped:15}}

______________________________________________
R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Received on Sun 22 Mar 2009 - 17:31:18 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Sun 22 Mar 2009 - 18:30:32 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive